INDEX

Explanations

instances of the word "apparent," indicating recognition or acknowledgment of observations or situations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

à¸Ľà¸£à¸°à¸Īà¸³

-0.17

essen

-0.16

ulet

-0.15

uet

-0.15

WISE

-0.14

shal

-0.14

Úĺ

-0.14

Zur

-0.14

illet

-0.13

/gtest

-0.13

POSITIVE LOGITS

azio

0.17

ikan

0.15

ileo

0.15

ODY

0.15

amo

0.15

anya

0.14

 Hughes

0.14

seudo

0.14

taj

0.14

orney

0.14

Activations Density 0.008%

instances of the word "apparent," indicating recognition or acknowledgment of observations or situations

No Comments

No Known Activations